Policy Configuration Method and Device

Abstract

The present disclosure provides a policy configuration method and apparatus. The method includes extracting corresponding input item tags according to third-party interface data, where the input item tags include policy tags and / or model tags; based on the policy tags and / or model tags, matching a policy model corresponding to the model tags on a preset model matching platform, and obtaining a model score of the policy model; based on the model score, on a preset policy configuration platform, allocating a competing policy and policy configuration data corresponding to the model score. The method of the present disclosure effectively solves a series of pain points such as RTA policy configuration, idle running, and monitoring, and constructs a full-life cycle management of policy configuration - policy verification - policy idle running - policy online - policy monitoring - policy offline. The policy has high concurrent efficiency, friendly interface interaction, and convenient and flexible migration in the production link.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technologies, and in particular, to a policy configuration method and apparatus. Background Art

[0002] With the development of Internet technologies, advertising platforms are not limited to roadside billboards and TV channels. Electronic products such as mobile phones, computers, and tablets have all become advertising platforms. For example, when we use software such as videos, games, or learning on mobile phones, advertisements may pop up. Currently, the most commonly used technology in the field of advertising is RTA (Real Time API) technology, which can be used to meet the real-time personalized delivery of advertisers.

[0003] In the existing advertising delivery based on RTA technology, it is often difficult to select a suitable strategy. For the selected strategy, it is difficult to match appropriate configuration parameters, and there is no suitable technical solution for the entire life cycle of RTA technology-based advertising delivery.

[0004] The information disclosed in the background art section of this application is only intended to deepen the understanding of the general background art of this application, and should not be regarded as an admission or any form of suggestion that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] Embodiments of the present disclosure provide a policy configuration method and apparatus, which can at least solve some problems in the prior art.

[0006] In a first aspect of the embodiments of the present disclosure, a policy configuration method is provided, including:

[0007] Extract the corresponding input item tags according to the third-party interface data, where the input item tags include policy tags and / or model tags;

[0008] Based on the policy tags and / or model tags, match the policy model corresponding to the model tags on a preset model matching platform, and obtain the model score of the policy model;

[0009] Based on the model score, allocate the competing policies and policy configuration data corresponding to the model score on a preset policy configuration platform.

[0010] In an optional implementation manner,

[0011] The input item tags include model tags, and the method for extracting the corresponding input item tags according to the third-party interface data includes:

[0012] Based on a pre-set log landing form, store the third-party interface data in a pre-set data warehouse, and extract model tags corresponding to the third-party interface data from the data warehouse.

[0013] In an alternative embodiment,

[0014] The model matching platform includes a third-party policy model and a platform policy model.

[0015] A method for matching a policy model corresponding to the model tag based on a pre-set model matching platform according to the policy tag and / or model tag includes:

[0016] According to the policy tag, match a third-party policy model corresponding to the model tag based on a pre-set model matching platform; and / or

[0017] According to the model tag, match a platform policy model corresponding to the model tag based on a pre-set model matching platform.

[0018] In an alternative embodiment,

[0019] A method for allocating a competing strategy and policy configuration data corresponding to the model score based on a pre-set policy configuration platform includes:

[0020] According to the model score, match a policy interval to which the model score belongs in a pre-set score policy correspondence relationship in a pre-set policy configuration platform;

[0021] Determine the predicted conversion rate corresponding to each alternative strategy in the policy interval, and use the alternative strategy with the highest matching degree between the predicted conversion rate and the model score among the alternative strategies as the competing strategy.

[0022] In an alternative embodiment,

[0023] After allocating the competing strategy and policy configuration data corresponding to the model score, the method further includes:

[0024] Configure the competing strategy based on the allocated competing strategy and policy configuration data;

[0025] Run the configured competing strategy without actual traffic and start a traffic pool experiment bucket corresponding to the competing strategy;

[0026] Monitor the empty-run result of the competing strategy and determine the competing rate and the stability of the competing strategy corresponding to the competing strategy.

[0027] In a second aspect of the embodiments of the present disclosure, a policy configuration device is provided, and the device includes:

[0028] The first unit is used to extract the corresponding input item tags according to the third - party interface data, wherein the input item tags include policy tags and / or model tags;

[0029] The second unit is used to match the policy model corresponding to the model tag based on a preset model matching platform according to the policy tag and / or model tag, and obtain the model score of the policy model;

[0030] The third unit is used to allocate the competing strategy and policy configuration data corresponding to the model score based on a preset policy configuration platform according to the model score.

[0031] In an alternative embodiment,

[0032] The input item tags include model tags,

[0033] The first unit is further used to:

[0034] Based on a preset log table, store the third - party interface data in a preset data warehouse, and extract the model tags corresponding to the third - party interface data from the data warehouse.

[0035] In an alternative embodiment,

[0036] The model matching platform includes a third - party policy model and a platform policy model,

[0037] The second unit is further used to:

[0038] According to the policy tag, match the third - party policy model corresponding to the model tag based on a preset model matching platform; and / or

[0039] According to the model tag, match the platform policy model corresponding to the model tag based on a preset model matching platform.

[0040] In an alternative embodiment,

[0041] The third unit is further used to:

[0042] According to the model score, match the policy interval to which the model score belongs in the preset score - policy correspondence relationship in a preset policy configuration platform;

[0043] Determine the predicted conversion rate corresponding to each alternative strategy in the policy interval, and use the alternative strategy with the highest matching degree between the predicted conversion rate and the model score among the alternative strategies as the competing strategy.

[0044] In an alternative embodiment,

[0045] The device further includes a fourth unit, and the fourth unit is configured to:

[0046] Configure the competing strategy based on the assigned competing strategy and the strategy configuration data;

[0047] Run the configured competing strategy without actual traffic and start the traffic pool experiment bucketing corresponding to the competing strategy;

[0048] Monitor the results of running the competing strategy without actual traffic, and determine the competing rate corresponding to the competing strategy and the stability of the competing strategy.

[0049] An embodiment of the present disclosure provides a strategy configuration method, and the method includes:

[0050] Extract the corresponding input item tags according to the third-party interface data, where the input item tags include strategy tags and / or model tags;

[0051] According to the strategy tags and / or model tags, based on a preset model matching platform, match the strategy model corresponding to the model tags and obtain the model scores of the strategy model;

[0052] According to the model scores, based on a preset strategy configuration platform, allocate the competing strategy corresponding to the model scores and the strategy configuration data.

[0053] The method of the present disclosure effectively solves a series of pain points such as RTA strategy configuration, running without actual traffic, and monitoring, and constructs a full life cycle management of strategy configuration - strategy verification - running without actual traffic - strategy online - strategy monitoring - strategy offline. The strategy has high concurrent efficiency, friendly interface interaction, and convenient and flexible migration in the production link. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flowchart of the strategy configuration method according to an embodiment of the present disclosure;

[0055] Figure 2 It is a logical diagram of the strategy configuration method according to an embodiment of the present disclosure;

[0056] Figure 3 It is the first specific example diagram of the strategy configuration according to an embodiment of the present disclosure;

[0057] Figure 4 It is the second specific example diagram of the strategy configuration according to an embodiment of the present disclosure;

[0058] Figure 5 It is a structural diagram of the strategy configuration device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are only a part rather than all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.

[0060] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present disclosure and the above-mentioned accompanying drawings are used to distinguish similar objects and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein.

[0061] It should be understood that in various embodiments of the present disclosure, the magnitude of the serial numbers of the various processes does not mean the sequence of execution, and the execution sequence of the various processes should be determined by their functions and internal logics, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

[0062] It should be understood that in the present disclosure, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0063] It should be understood that in the present disclosure, "a plurality of" means two or more. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. "Including A, B, and C" and "including A, B, C" mean that all of A, B, and C are included. "Including A, B, or C" means including any one of A, B, and C. "Including A, B, and / or C" means including any one, any two, or all three of A, B, and C.

[0064] It should be understood that in the present disclosure, "B corresponding to A", "B corresponding to A relatively", "A corresponding to B relatively", or "B corresponding to A relatively" means that B is associated with A, and B can be determined according to A. Determining B according to A does not mean determining B only according to A, but B can also be determined according to A and / or other information. The matching of A and B means that the similarity between A and B is greater than or equal to a preset threshold.

[0065] Depending on the context, as used herein, "if" can be interpreted as "when", "while", "in response to determining", or "in response to detecting".

[0066] The technical solutions of the present disclosure will be described in detail below with specific embodiments. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0067] Figure 1 Exemplarily, a flowchart of a strategy configuration method according to an embodiment of the present disclosure is shown, as Figure 1 shown, the method includes:

[0068] S101. Extract the corresponding input item tags according to the third-party interface data, where the input item tags include policy tags and / or model tags;

[0069] Exemplarily, the advertisement placement method can be implemented based on RTA (Real Time API) technology. RTA is a real-time advertisement program interface, which provides a data interface for the advertisement placement platform. Based on the RTA interface, the advertisement placement platform can obtain advertisement platform device information, and then determine whether to place an advertisement on the advertisement platform device information by determining whether the advertisement platform device information is the advertisement platform device information that the advertiser needs to place an advertisement.

[0070] In the RTA mode, the resource trading platform can select traffic, but the selection of traffic in the RTA mode only involves selections such as click conversion for resource bidding, and does not perform backend or entire resource full-link conversion selection, that is, to create real value for resource providers or resource demanders.

[0071] In an alternative embodiment,

[0072] the input item tags include model tags, and the method for extracting the corresponding input item tags according to the third-party interface data includes:

[0073] Based on a pre-set log landing table, store the third-party interface data in a preset data warehouse, and extract the model tags corresponding to the third-party interface data from the data warehouse.

[0074] Exemplarily, the input item tags of the embodiments of the present disclosure may include policy tags and / or model tags, where the input item tags may include the device number of the third-party data and the feature tags of the third-party data. Generally speaking, it is the ID card of the third-party data.

[0075] Among them, the policy label is the label used to directly select the policy; the model label is the label used to select the model corresponding to the third-party data.

[0076] Optionally, the log table is used to record the data call process of the third-party data and record it in the form of a log table; in addition, the data warehouse is combined for data storage so that the originally discrete third-party data can be subjected to data aggregation analysis.

[0077] Among them, the model label in the third-party data can also be directly extracted and directly input into a preset model matching platform to match the policy model corresponding to the model label.

[0078] S102. According to the policy label and / or model label, based on a preset model matching platform, match the policy model corresponding to the model label and obtain the model score of the policy model;

[0079] Optionally, the model matching platform of the embodiments of the present disclosure may include a third-party policy model and a platform policy model, where

[0080] The third-party policy model may exist independently of the model matching platform or may be incorporated into the model matching platform;

[0081] In an alternative embodiment,

[0082] The model matching platform includes a third-party policy model and a platform policy model,

[0083] The method for matching the policy model corresponding to the model label according to the policy label and / or model label based on a preset model matching platform includes:

[0084] According to the policy label, based on a preset model matching platform, match the third-party policy model corresponding to the model label; and / or

[0085] According to the model label, based on a preset model matching platform, match the platform policy model corresponding to the model label.

[0086] Exemplarily, for the policy label, the corresponding third-party policy model can be directly matched according to the model matching platform, while for the model label, the platform policy model corresponding to the model label needs to be matched first, and the corresponding score is output according to the platform policy model.

[0087] It should be noted that both the third-party policy model and the platform policy model of the embodiments of the present disclosure can output corresponding scores according to the corresponding labels. Among them, the scores output by the models correspond to the relevance of the labels. The third-party policy model and the platform policy model can output corresponding scores according to the feature vectors corresponding to the labels.

[0088] S103. Based on the preset policy configuration platform according to the model score, allocate a participation competition strategy and policy configuration data corresponding to the model score.

[0089] In an alternative embodiment,

[0090] The method for allocating a participation competition strategy and policy configuration data corresponding to the model score based on the preset policy configuration platform includes:

[0091] According to the model score, based on the preset score - strategy correspondence in the policy configuration platform, match the policy interval to which the model score belongs in the score - strategy correspondence;

[0092] Determine the predicted conversion rates corresponding to each alternative strategy in the policy interval, and use the alternative strategy with the highest matching degree between the predicted conversion rate and the model score among the alternative strategies as the participation competition strategy.

[0093] In an alternative embodiment,

[0094] After allocating the participation competition strategy and policy configuration data corresponding to the model score, the method further includes:

[0095] Configure the participation competition strategy based on the allocated participation competition strategy and policy configuration data;

[0096] Run the configured participation competition strategy without real - time data input, and start the traffic pool experiment bucketing corresponding to the participation competition strategy;

[0097] Monitor the results of running the participation competition strategy without real - time data input, and determine the participation rate corresponding to the participation competition strategy and the stability of the participation competition strategy.

[0098] Figure 2 Exemplarily show the logical schematic diagram of the policy configuration method of the embodiments of the present disclosure, Figure 3 It is the first specific example diagram of the policy configuration of the embodiments of the present disclosure; Figure 4 It is the second specific example diagram of the policy configuration of the embodiments of the present disclosure;

[0099] As Figure 2 shown, the method includes:

[0100] Configure the input item tags after processing the third - party interface data used by RTA through the RTA data platform into the RTA policy platform, and sequentially configure the results after predicting the model scores used by the RTA policy through the RTA model platform into the RTA policy platform;

[0101] According to the specific content of the RTA strategy, accurately configure it into the policy configuration computing device, where the model prediction results are preprocessed in the computing device before policy configuration;

[0102] Verify the strategy, the policy configuration result and the policy decision result on the policy summary dashboard. After verification, start the dry run of the strategy and bind the traffic pool experiment bucket, and start the policy monitoring device;

[0103] View the dry run results of the strategy, the participation rate and the proportion of the bid coefficient, the stability of the strategy, etc. in the policy monitoring device;

[0104] On the other hand, there is a policy encoding and policy call flow device, which mainly manages and calls the policy configuration device and performs encoding management to facilitate subsequent effect analysis and modular reuse and deactivation of the strategy.

[0105] The embodiments of the present disclosure provide a policy configuration method, and the method includes:

[0106] Extract the corresponding input item tags according to the third-party interface data, where the input item tags include policy tags and / or model tags;

[0107] According to the policy tags and / or model tags, based on a preset model matching platform, match the policy model corresponding to the model tag, and obtain the model score of the policy model;

[0108] According to the model score, based on a preset policy configuration platform, allocate the participation strategy and policy configuration data corresponding to the model score.

[0109] The method of the present disclosure effectively solves a series of pain points such as RTA policy configuration, dry run and monitoring, and constructs a full life cycle management of policy configuration - policy verification - policy dry run - policy online - policy monitoring - policy offline. The policy has high concurrent efficiency, friendly interface interaction and convenient and flexible migration in the production link.

[0110] Figure 5 Exemplarily show the structural schematic diagram of the policy configuration device of the embodiments of the present disclosure, as Figure 5 shown, the device includes:

[0111] The first unit 51 is used to extract the corresponding input item tags according to the third-party interface data, where the input item tags include policy tags and / or model tags;

[0112] The second unit 52 is used to match the policy model corresponding to the model tag based on a preset model matching platform according to the policy tags and / or model tags, and obtain the model score of the policy model;

[0113] The third unit 53 is used to allocate a participation competition strategy and strategy configuration data corresponding to the model score based on a preset policy configuration platform according to the model score.

[0114] In an alternative embodiment,

[0115] The input item label includes a model label,

[0116] The first unit 51 is further used for:

[0117] Based on a preset log table, store the third-party interface data into a preset data warehouse, and extract the model label corresponding to the third-party interface data from the data warehouse.

[0118] In an alternative embodiment,

[0119] The model matching platform includes a third-party policy model and a platform policy model,

[0120] The second unit 52 is further used for:

[0121] According to the policy label, match a third-party policy model corresponding to the model label based on a preset model matching platform; and / or

[0122] According to the model label, match a platform policy model corresponding to the model label based on a preset model matching platform.

[0123] In an alternative embodiment,

[0124] The third unit 53 is further used for:

[0125] According to the model score, match the policy interval to which the model score belongs in the preset score policy correspondence relationship in the preset policy configuration platform;

[0126] Determine the predicted conversion rates corresponding to each alternative strategy in the policy interval, and use the alternative strategy with the highest matching degree between the predicted conversion rate and the model score among the alternative strategies as the participation competition strategy.

[0127] In an alternative embodiment,

[0128] The device further includes a fourth unit 54, and the fourth unit 54 is used for:

[0129] Configure the participation competition strategy based on the allocated participation competition strategy and strategy configuration data;

[0130] Run the configured participation competition strategy without actual data and start the traffic pool experiment bucketing corresponding to the participation competition strategy;

[0131] Monitor the idle running results of the competing strategy, and determine the competition rate corresponding to the competing strategy and the stability of the competing strategy.

[0132] It should be noted that the beneficial effects of the strategy configuration device in the embodiments of the present disclosure can refer to the beneficial effects of the foregoing strategy configuration method, and will not be elaborated herein in the embodiments of the present disclosure.

[0133] The present invention may be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for performing various aspects of the present invention.

[0134] A computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punched card or raised structures in a groove having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0135] The computer-readable program instructions described herein can be downloaded from the computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. The network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0136] The computer program instructions for carrying out the operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present invention.

[0137] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer - readable program instructions.

[0138] These computer - readable program instructions can be provided to a processing unit of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine, such that when the instructions are executed by the processing unit of the computer or other programmable data - processing apparatus, a device is produced that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions includes a manufacture, which includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0139] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to generate a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0140] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0141] Note that unless otherwise directly stated, all features disclosed in this specification (including any appended claims, abstract, and drawings) may be replaced by alternative features serving the same, equivalent, or similar purpose. Therefore, unless otherwise explicitly stated, each feature disclosed is only an example of a group of equivalent or similar features. When used, further, preferably, furthermore, and more preferably are simple introductions for elaborating another embodiment based on the foregoing embodiments. The content following the further, preferably, furthermore, or more preferably, in combination with the foregoing embodiments, constitutes a complete composition of another embodiment. Combinations can be arbitrarily made among several further, preferably, furthermore, or more preferably settings following the same embodiment to form another embodiment.

[0142] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been shown and described in the embodiments. Without departing from the principles described, the embodiments of the present invention may be subject to any deformation or modification.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A strategy configuration method, characterized in that, Including: Extracting corresponding input item labels according to third - party interface data, where the input item labels include policy labels and / or model labels; Based on the policy labels and / or model labels, matching a policy model corresponding to the model label on a preset model matching platform, and obtaining the model score of the policy model; Based on the model score, matching the policy interval to which the model score belongs in the preset score - policy correspondence relationship in a preset policy configuration platform; Determining the predicted conversion rates corresponding to each alternative policy in the policy interval, and taking the alternative policy with the highest matching degree between the predicted conversion rate and the model score among the alternative policies as the competing policy.

2. The method according to claim 1, wherein The input item labels include model labels, and the method for extracting corresponding input item labels according to third - party interface data includes: Based on a pre - set log landing form, storing the third - party interface data in a preset data warehouse, and extracting the model label corresponding to the third - party interface data from the data warehouse.

3. The method according to claim 1, wherein The model matching platform includes a third - party policy model and a platform policy model, Based on the policy labels and / or model labels, the method for matching a policy model corresponding to the model label on a preset model matching platform includes: Based on the policy label, matching a third - party policy model corresponding to the model label on a preset model matching platform; and / or Based on the model label, matching a platform policy model corresponding to the model label on a preset model matching platform.

4. The method according to claim 1, characterized in that, After taking the alternative policy with the highest matching degree between the predicted conversion rate and the model score among the alternative policies as the competing policy, the method further includes: Configuring the competing policy based on the assigned competing policy and policy configuration data; Running the configured competing policy in an empty - run mode, and opening a traffic pool experiment bucket corresponding to the competing policy; Monitoring the empty - run result of the competing policy, and determining the competition rate corresponding to the competing policy and the stability of the competing policy.

5. A policy configuration device, characterized in that, The device includes: A first unit for extracting corresponding input item labels according to third - party interface data, where the input item labels include policy labels and / or model labels; A second unit for matching a policy model corresponding to the model label based on the policy labels and / or model labels on a preset model matching platform, and obtaining the model score of the policy model; A third unit for, based on the model score, matching the policy interval to which the model score belongs in the preset score - policy correspondence relationship in a preset policy configuration platform; determining the predicted conversion rates corresponding to each alternative policy in the policy interval, and taking the alternative policy with the highest matching degree between the predicted conversion rate and the model score among the alternative policies as the competing policy.

6. The device according to claim 5, characterized in that, The input item labels include model labels, ​ ​ 7. The device according to claim 5, characterized in that, The model matching platform includes a third-party policy model and a platform policy model. The second unit is further configured to: Based on the policy label, match a third-party policy model corresponding to the model label based on a preset model matching platform; and / or Based on the model label, match a platform policy model corresponding to the model label based on a preset model matching platform.

8. The device according to claim 5, characterized in that, The apparatus further includes a fourth unit, and the fourth unit is configured to: Configure the competing policy based on the allocated competing policy and policy configuration data; Run the configured competing policy without actual traffic and start the traffic pool experiment bucketing corresponding to the competing policy; Monitor the result of running the competing policy without actual traffic, and determine the competing rate corresponding to the competing policy and the stability of the competing policy.

Images